2005-04-17 06:20:36 +08:00
|
|
|
/*
|
2009-04-28 06:27:18 +08:00
|
|
|
* Suspend support specific for i386/x86-64.
|
2005-04-17 06:20:36 +08:00
|
|
|
*
|
|
|
|
* Distribute under GPLv2
|
|
|
|
*
|
2008-02-10 06:24:09 +08:00
|
|
|
* Copyright (c) 2007 Rafael J. Wysocki <rjw@sisk.pl>
|
2010-07-18 20:27:13 +08:00
|
|
|
* Copyright (c) 2002 Pavel Machek <pavel@ucw.cz>
|
2005-04-17 06:20:36 +08:00
|
|
|
* Copyright (c) 2001 Patrick Mochel <mochel@osdl.org>
|
|
|
|
*/
|
|
|
|
|
|
|
|
#include <linux/suspend.h>
|
2011-05-27 00:22:53 +08:00
|
|
|
#include <linux/export.h>
|
2009-04-28 06:26:22 +08:00
|
|
|
#include <linux/smp.h>
|
2013-03-15 21:26:07 +08:00
|
|
|
#include <linux/perf_event.h>
|
2009-04-28 06:26:22 +08:00
|
|
|
|
[PATCH] x86_64: Set up safe page tables during resume
The following patch makes swsusp avoid the possible temporary corruption
of page translation tables during resume on x86-64. This is achieved by
creating a copy of the relevant page tables that will not be modified by
swsusp and can be safely used by it on resume.
The problem is that during resume on x86-64 swsusp may temporarily
corrupt the page tables used for the direct mapping of RAM. If that
happens, a page fault occurs and cannot be handled properly, which leads
to the solid hang of the affected system. This leads to the loss of the
system's state from before suspend and may result in the loss of data or
the corruption of filesystems, so it is a serious issue. Also, it
appears to happen quite often (for me, as often as 50% of the time).
The problem is related to the fact that (at least) one of the PMD
entries used in the direct memory mapping (starting at PAGE_OFFSET)
points to a page table the physical address of which is much greater
than the physical address of the PMD entry itself. Moreover,
unfortunately, the physical address of the page table before suspend
(i.e. the one stored in the suspend image) happens to be different to
the physical address of the corresponding page table used during resume
(i.e. the one that is valid right before swsusp_arch_resume() in
arch/x86_64/kernel/suspend_asm.S is executed). Thus while the image is
restored, the "offending" PMD entry gets overwritten, so it does not
point to the right physical address any more (i.e. there's no page
table at the address pointed to by it, because it points to the address
the page table has been at during suspend). Consequently, if the PMD
entry is used later on, and it _is_ used in the process of copying the
image pages, a page fault occurs, but it cannot be handled in the normal
way and the system hangs.
In principle we can call create_resume_mapping() from
swsusp_arch_resume() (ie. from suspend_asm.S), but then the memory
allocations in create_resume_mapping(), resume_pud_mapping(), and
resume_pmd_mapping() must be made carefully so that we use _only_
NosaveFree pages in them (the other pages are overwritten by the loop in
swsusp_arch_resume()). Additionally, we are in atomic context at that
time, so we cannot use GFP_KERNEL. Moreover, if one of the allocations
fails, we should free all of the allocated pages, so we need to trace
them somehow.
All of this is done in the appended patch, except that the functions
populating the page tables are located in arch/x86_64/kernel/suspend.c
rather than in init.c. It may be done in a more elegan way in the
future, with the help of some swsusp patches that are in the works now.
[AK: move some externs into headers, renamed a function]
Signed-off-by: Rafael J. Wysocki <rjw@sisk.pl>
Signed-off-by: Andi Kleen <ak@suse.de>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-10-10 03:19:40 +08:00
|
|
|
#include <asm/pgtable.h>
|
2009-04-28 06:26:22 +08:00
|
|
|
#include <asm/proto.h>
|
2007-05-03 01:27:17 +08:00
|
|
|
#include <asm/mtrr.h>
|
2009-04-28 06:26:22 +08:00
|
|
|
#include <asm/page.h>
|
|
|
|
#include <asm/mce.h>
|
2009-04-01 06:23:37 +08:00
|
|
|
#include <asm/suspend.h>
|
2009-06-02 02:14:26 +08:00
|
|
|
#include <asm/debugreg.h>
|
2012-11-14 03:32:51 +08:00
|
|
|
#include <asm/cpu.h>
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2009-04-28 06:26:50 +08:00
|
|
|
#ifdef CONFIG_X86_32
|
2013-08-06 06:02:49 +08:00
|
|
|
__visible unsigned long saved_context_ebx;
|
|
|
|
__visible unsigned long saved_context_esp, saved_context_ebp;
|
|
|
|
__visible unsigned long saved_context_esi, saved_context_edi;
|
|
|
|
__visible unsigned long saved_context_eflags;
|
2009-04-28 06:26:50 +08:00
|
|
|
#endif
|
2013-05-02 09:53:30 +08:00
|
|
|
struct saved_context saved_context;
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2008-01-30 20:30:04 +08:00
|
|
|
/**
|
|
|
|
* __save_processor_state - save CPU registers before creating a
|
|
|
|
* hibernation image and before restoring the memory state from it
|
|
|
|
* @ctxt - structure to store the registers contents in
|
|
|
|
*
|
|
|
|
* NOTE: If there is a CPU register the modification of which by the
|
|
|
|
* boot kernel (ie. the kernel used for loading the hibernation image)
|
|
|
|
* might affect the operations of the restored target kernel (ie. the one
|
|
|
|
* saved in the hibernation image), then its contents must be saved by this
|
|
|
|
* function. In other words, if kernel A is hibernated and different
|
|
|
|
* kernel B is used for loading the hibernation image into memory, the
|
|
|
|
* kernel A's __save_processor_state() function must save all registers
|
|
|
|
* needed by kernel A, so that it can operate correctly after the resume
|
|
|
|
* regardless of what kernel B does in the meantime.
|
|
|
|
*/
|
2008-01-30 20:31:23 +08:00
|
|
|
static void __save_processor_state(struct saved_context *ctxt)
|
2005-04-17 06:20:36 +08:00
|
|
|
{
|
2009-04-28 06:27:00 +08:00
|
|
|
#ifdef CONFIG_X86_32
|
|
|
|
mtrr_save_fixed_ranges(NULL);
|
|
|
|
#endif
|
2005-04-17 06:20:36 +08:00
|
|
|
kernel_fpu_begin();
|
|
|
|
|
|
|
|
/*
|
|
|
|
* descriptor tables
|
|
|
|
*/
|
2009-04-28 06:27:00 +08:00
|
|
|
#ifdef CONFIG_X86_32
|
|
|
|
store_idt(&ctxt->idt);
|
|
|
|
#else
|
|
|
|
/* CONFIG_X86_64 */
|
2007-10-20 02:35:03 +08:00
|
|
|
store_idt((struct desc_ptr *)&ctxt->idt_limit);
|
2009-04-28 06:27:00 +08:00
|
|
|
#endif
|
2013-05-02 09:53:30 +08:00
|
|
|
/*
|
|
|
|
* We save it here, but restore it only in the hibernate case.
|
|
|
|
* For ACPI S3 resume, this is loaded via 'early_gdt_desc' in 64-bit
|
|
|
|
* mode in "secondary_startup_64". In 32-bit mode it is done via
|
|
|
|
* 'pmode_gdt' in wakeup_start.
|
|
|
|
*/
|
|
|
|
ctxt->gdt_desc.size = GDT_SIZE - 1;
|
|
|
|
ctxt->gdt_desc.address = (unsigned long)get_cpu_gdt_table(smp_processor_id());
|
|
|
|
|
2007-10-20 02:35:03 +08:00
|
|
|
store_tr(ctxt->tr);
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
/* XMM0..XMM15 should be handled by kernel_fpu_begin(). */
|
|
|
|
/*
|
|
|
|
* segment registers
|
|
|
|
*/
|
2009-04-28 06:27:00 +08:00
|
|
|
#ifdef CONFIG_X86_32
|
|
|
|
savesegment(es, ctxt->es);
|
|
|
|
savesegment(fs, ctxt->fs);
|
|
|
|
savesegment(gs, ctxt->gs);
|
|
|
|
savesegment(ss, ctxt->ss);
|
|
|
|
#else
|
|
|
|
/* CONFIG_X86_64 */
|
2005-04-17 06:20:36 +08:00
|
|
|
asm volatile ("movw %%ds, %0" : "=m" (ctxt->ds));
|
|
|
|
asm volatile ("movw %%es, %0" : "=m" (ctxt->es));
|
|
|
|
asm volatile ("movw %%fs, %0" : "=m" (ctxt->fs));
|
|
|
|
asm volatile ("movw %%gs, %0" : "=m" (ctxt->gs));
|
|
|
|
asm volatile ("movw %%ss, %0" : "=m" (ctxt->ss));
|
|
|
|
|
|
|
|
rdmsrl(MSR_FS_BASE, ctxt->fs_base);
|
|
|
|
rdmsrl(MSR_GS_BASE, ctxt->gs_base);
|
|
|
|
rdmsrl(MSR_KERNEL_GS_BASE, ctxt->gs_kernel_base);
|
2007-05-03 01:27:17 +08:00
|
|
|
mtrr_save_fixed_ranges(NULL);
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2009-04-28 06:27:00 +08:00
|
|
|
rdmsrl(MSR_EFER, ctxt->efer);
|
|
|
|
#endif
|
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
/*
|
2008-02-10 06:24:09 +08:00
|
|
|
* control registers
|
2005-04-17 06:20:36 +08:00
|
|
|
*/
|
2007-07-22 17:12:29 +08:00
|
|
|
ctxt->cr0 = read_cr0();
|
|
|
|
ctxt->cr2 = read_cr2();
|
|
|
|
ctxt->cr3 = read_cr3();
|
2014-10-25 06:58:08 +08:00
|
|
|
ctxt->cr4 = __read_cr4_safe();
|
|
|
|
#ifdef CONFIG_X86_64
|
2007-07-22 17:12:29 +08:00
|
|
|
ctxt->cr8 = read_cr8();
|
2009-04-28 06:27:00 +08:00
|
|
|
#endif
|
2010-06-08 06:32:49 +08:00
|
|
|
ctxt->misc_enable_saved = !rdmsrl_safe(MSR_IA32_MISC_ENABLE,
|
|
|
|
&ctxt->misc_enable);
|
2005-04-17 06:20:36 +08:00
|
|
|
}
|
|
|
|
|
2009-04-28 06:27:00 +08:00
|
|
|
/* Needed by apm.c */
|
2005-04-17 06:20:36 +08:00
|
|
|
void save_processor_state(void)
|
|
|
|
{
|
|
|
|
__save_processor_state(&saved_context);
|
2012-02-13 21:07:27 +08:00
|
|
|
x86_platform.save_sched_clock_state();
|
2005-04-17 06:20:36 +08:00
|
|
|
}
|
2009-04-28 06:27:00 +08:00
|
|
|
#ifdef CONFIG_X86_32
|
|
|
|
EXPORT_SYMBOL(save_processor_state);
|
|
|
|
#endif
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2005-10-31 06:59:28 +08:00
|
|
|
static void do_fpu_end(void)
|
2005-04-17 06:20:36 +08:00
|
|
|
{
|
2005-10-31 06:59:28 +08:00
|
|
|
/*
|
2009-04-28 06:27:05 +08:00
|
|
|
* Restore FPU regs if necessary.
|
2005-10-31 06:59:28 +08:00
|
|
|
*/
|
|
|
|
kernel_fpu_end();
|
2005-04-17 06:20:36 +08:00
|
|
|
}
|
|
|
|
|
2009-04-28 06:27:05 +08:00
|
|
|
static void fix_processor_context(void)
|
|
|
|
{
|
|
|
|
int cpu = smp_processor_id();
|
2015-03-06 11:19:05 +08:00
|
|
|
struct tss_struct *t = &per_cpu(cpu_tss, cpu);
|
2013-04-06 04:42:24 +08:00
|
|
|
#ifdef CONFIG_X86_64
|
|
|
|
struct desc_struct *desc = get_cpu_gdt_table(cpu);
|
|
|
|
tss_desc tss;
|
|
|
|
#endif
|
2009-04-28 06:27:05 +08:00
|
|
|
set_tss_desc(cpu, t); /*
|
|
|
|
* This just modifies memory; should not be
|
|
|
|
* necessary. But... This is necessary, because
|
|
|
|
* 386 hardware has concept of busy TSS or some
|
|
|
|
* similar stupidity.
|
|
|
|
*/
|
|
|
|
|
|
|
|
#ifdef CONFIG_X86_64
|
2013-04-06 04:42:24 +08:00
|
|
|
memcpy(&tss, &desc[GDT_ENTRY_TSS], sizeof(tss_desc));
|
|
|
|
tss.type = 0x9; /* The available 64-bit TSS (see AMD vol 2, pg 91 */
|
|
|
|
write_gdt_entry(desc, GDT_ENTRY_TSS, &tss, DESC_TSS);
|
2009-04-28 06:27:05 +08:00
|
|
|
|
|
|
|
syscall_init(); /* This sets MSR_*STAR and related */
|
|
|
|
#endif
|
|
|
|
load_TR_desc(); /* This does ltr */
|
|
|
|
load_LDT(¤t->active_mm->context); /* This does lldt */
|
2015-04-24 16:02:32 +08:00
|
|
|
|
|
|
|
fpu__resume_cpu();
|
2009-04-28 06:27:05 +08:00
|
|
|
}
|
|
|
|
|
2008-01-30 20:30:04 +08:00
|
|
|
/**
|
|
|
|
* __restore_processor_state - restore the contents of CPU registers saved
|
|
|
|
* by __save_processor_state()
|
|
|
|
* @ctxt - structure to load the registers contents from
|
|
|
|
*/
|
2014-06-25 08:58:26 +08:00
|
|
|
static void notrace __restore_processor_state(struct saved_context *ctxt)
|
2005-04-17 06:20:36 +08:00
|
|
|
{
|
2010-06-08 06:32:49 +08:00
|
|
|
if (ctxt->misc_enable_saved)
|
|
|
|
wrmsrl(MSR_IA32_MISC_ENABLE, ctxt->misc_enable);
|
2005-04-17 06:20:36 +08:00
|
|
|
/*
|
|
|
|
* control registers
|
|
|
|
*/
|
2009-04-28 06:27:05 +08:00
|
|
|
/* cr4 was introduced in the Pentium CPU */
|
|
|
|
#ifdef CONFIG_X86_32
|
|
|
|
if (ctxt->cr4)
|
2014-10-25 06:58:08 +08:00
|
|
|
__write_cr4(ctxt->cr4);
|
2009-04-28 06:27:05 +08:00
|
|
|
#else
|
|
|
|
/* CONFIG X86_64 */
|
2007-05-03 01:27:07 +08:00
|
|
|
wrmsrl(MSR_EFER, ctxt->efer);
|
2007-07-22 17:12:29 +08:00
|
|
|
write_cr8(ctxt->cr8);
|
2014-10-25 06:58:08 +08:00
|
|
|
__write_cr4(ctxt->cr4);
|
2009-04-28 06:27:05 +08:00
|
|
|
#endif
|
2007-07-22 17:12:29 +08:00
|
|
|
write_cr3(ctxt->cr3);
|
|
|
|
write_cr2(ctxt->cr2);
|
|
|
|
write_cr0(ctxt->cr0);
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2005-06-26 05:55:14 +08:00
|
|
|
/*
|
|
|
|
* now restore the descriptor tables to their proper values
|
|
|
|
* ltr is done i fix_processor_context().
|
|
|
|
*/
|
2009-04-28 06:27:05 +08:00
|
|
|
#ifdef CONFIG_X86_32
|
|
|
|
load_idt(&ctxt->idt);
|
|
|
|
#else
|
|
|
|
/* CONFIG_X86_64 */
|
2007-10-20 02:35:03 +08:00
|
|
|
load_idt((const struct desc_ptr *)&ctxt->idt_limit);
|
2009-04-28 06:27:05 +08:00
|
|
|
#endif
|
2005-06-26 05:55:14 +08:00
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
/*
|
|
|
|
* segment registers
|
|
|
|
*/
|
2009-04-28 06:27:05 +08:00
|
|
|
#ifdef CONFIG_X86_32
|
|
|
|
loadsegment(es, ctxt->es);
|
|
|
|
loadsegment(fs, ctxt->fs);
|
|
|
|
loadsegment(gs, ctxt->gs);
|
|
|
|
loadsegment(ss, ctxt->ss);
|
|
|
|
|
|
|
|
/*
|
|
|
|
* sysenter MSRs
|
|
|
|
*/
|
|
|
|
if (boot_cpu_has(X86_FEATURE_SEP))
|
|
|
|
enable_sep_cpu();
|
|
|
|
#else
|
|
|
|
/* CONFIG_X86_64 */
|
2005-04-17 06:20:36 +08:00
|
|
|
asm volatile ("movw %0, %%ds" :: "r" (ctxt->ds));
|
|
|
|
asm volatile ("movw %0, %%es" :: "r" (ctxt->es));
|
|
|
|
asm volatile ("movw %0, %%fs" :: "r" (ctxt->fs));
|
|
|
|
load_gs_index(ctxt->gs);
|
|
|
|
asm volatile ("movw %0, %%ss" :: "r" (ctxt->ss));
|
|
|
|
|
|
|
|
wrmsrl(MSR_FS_BASE, ctxt->fs_base);
|
|
|
|
wrmsrl(MSR_GS_BASE, ctxt->gs_base);
|
|
|
|
wrmsrl(MSR_KERNEL_GS_BASE, ctxt->gs_kernel_base);
|
2009-04-28 06:27:05 +08:00
|
|
|
#endif
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
fix_processor_context();
|
|
|
|
|
|
|
|
do_fpu_end();
|
2012-04-02 00:53:36 +08:00
|
|
|
x86_platform.restore_sched_clock_state();
|
2009-08-20 09:05:36 +08:00
|
|
|
mtrr_bp_restore();
|
2013-03-15 21:26:07 +08:00
|
|
|
perf_restore_debug_store();
|
2005-04-17 06:20:36 +08:00
|
|
|
}
|
|
|
|
|
2009-04-28 06:27:05 +08:00
|
|
|
/* Needed by apm.c */
|
2014-06-25 08:58:26 +08:00
|
|
|
void notrace restore_processor_state(void)
|
2005-04-17 06:20:36 +08:00
|
|
|
{
|
|
|
|
__restore_processor_state(&saved_context);
|
|
|
|
}
|
2009-04-28 06:27:05 +08:00
|
|
|
#ifdef CONFIG_X86_32
|
|
|
|
EXPORT_SYMBOL(restore_processor_state);
|
|
|
|
#endif
|
2012-11-14 03:32:42 +08:00
|
|
|
|
|
|
|
/*
|
|
|
|
* When bsp_check() is called in hibernate and suspend, cpu hotplug
|
|
|
|
* is disabled already. So it's unnessary to handle race condition between
|
|
|
|
* cpumask query and cpu hotplug.
|
|
|
|
*/
|
|
|
|
static int bsp_check(void)
|
|
|
|
{
|
|
|
|
if (cpumask_first(cpu_online_mask) != 0) {
|
|
|
|
pr_warn("CPU0 is offline.\n");
|
|
|
|
return -ENODEV;
|
|
|
|
}
|
|
|
|
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
static int bsp_pm_callback(struct notifier_block *nb, unsigned long action,
|
|
|
|
void *ptr)
|
|
|
|
{
|
|
|
|
int ret = 0;
|
|
|
|
|
|
|
|
switch (action) {
|
|
|
|
case PM_SUSPEND_PREPARE:
|
|
|
|
case PM_HIBERNATION_PREPARE:
|
|
|
|
ret = bsp_check();
|
|
|
|
break;
|
2012-11-14 03:32:51 +08:00
|
|
|
#ifdef CONFIG_DEBUG_HOTPLUG_CPU0
|
|
|
|
case PM_RESTORE_PREPARE:
|
|
|
|
/*
|
|
|
|
* When system resumes from hibernation, online CPU0 because
|
|
|
|
* 1. it's required for resume and
|
|
|
|
* 2. the CPU was online before hibernation
|
|
|
|
*/
|
|
|
|
if (!cpu_online(0))
|
|
|
|
_debug_hotplug_cpu(0, 1);
|
|
|
|
break;
|
|
|
|
case PM_POST_RESTORE:
|
|
|
|
/*
|
|
|
|
* When a resume really happens, this code won't be called.
|
|
|
|
*
|
|
|
|
* This code is called only when user space hibernation software
|
|
|
|
* prepares for snapshot device during boot time. So we just
|
|
|
|
* call _debug_hotplug_cpu() to restore to CPU0's state prior to
|
|
|
|
* preparing the snapshot device.
|
|
|
|
*
|
|
|
|
* This works for normal boot case in our CPU0 hotplug debug
|
|
|
|
* mode, i.e. CPU0 is offline and user mode hibernation
|
|
|
|
* software initializes during boot time.
|
|
|
|
*
|
|
|
|
* If CPU0 is online and user application accesses snapshot
|
|
|
|
* device after boot time, this will offline CPU0 and user may
|
|
|
|
* see different CPU0 state before and after accessing
|
|
|
|
* the snapshot device. But hopefully this is not a case when
|
|
|
|
* user debugging CPU0 hotplug. Even if users hit this case,
|
|
|
|
* they can easily online CPU0 back.
|
|
|
|
*
|
|
|
|
* To simplify this debug code, we only consider normal boot
|
|
|
|
* case. Otherwise we need to remember CPU0's state and restore
|
|
|
|
* to that state and resolve racy conditions etc.
|
|
|
|
*/
|
|
|
|
_debug_hotplug_cpu(0, 0);
|
|
|
|
break;
|
|
|
|
#endif
|
2012-11-14 03:32:42 +08:00
|
|
|
default:
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
return notifier_from_errno(ret);
|
|
|
|
}
|
|
|
|
|
|
|
|
static int __init bsp_pm_check_init(void)
|
|
|
|
{
|
|
|
|
/*
|
|
|
|
* Set this bsp_pm_callback as lower priority than
|
|
|
|
* cpu_hotplug_pm_callback. So cpu_hotplug_pm_callback will be called
|
|
|
|
* earlier to disable cpu hotplug before bsp online check.
|
|
|
|
*/
|
|
|
|
pm_notifier(bsp_pm_callback, -INT_MAX);
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
core_initcall(bsp_pm_check_init);
|